Nature paper finds key misalignment between vision models and humans across abstraction levels
serrjoa · x · 2026-11-09
Researchers including Lukas Muttenthaler and Andrew Lampinen (Google DeepMind and partners) published an open-access Nature paper comparing deep network and human visual representations.
- Key finding: human conceptual knowledge is hierarchically organized across abstraction levels, while vision models lack this structure — possibly explaining why they generalize less robustly than humans.
- The paper offers a framework for aligning machine and human visual representations across abstraction levels.
- It has already drawn 72k accesses and 48 citations.
More from Models
- MathArena adds October BrokenArXiv: GPT-6.1 Sol leads but drifts down monthly, Opus 5.5 rock solid — teortaxesTex · 2026-11-09
- Users report Opus 5.5 back to normal, suspect Anthropic silently reverted the degradation — ryunuck · 2026-11-09
- Open-weights models now just 2 months behind closed frontier as Kimi K3.1 Pro lands — 0xsachi · 2026-11-09
- Model trained on 150,000 CVE exploits scores 88.4% on CyberGym with zero refusals — jedisct1 · 2026-11-09
- ChatGPT app appears to have nuked Chrome/browser tooling, leaving only computer use — GabGarrett · 2026-11-09
- Anthropic could start IPO roadshow as early as Tuesday, eyeing $1.1-1.3T valuation — kimmonismus · 2026-11-09